AI Agent Engineer

Air InfoSec•Austin, TX

15h•Hybrid

About The Position

The AI Agent Engineer will support the Texas Health and Human Services Commission (HHSC). This role is responsible for researching, designing, implementing, and managing AI -driven software solutions that enhance productivity, automate processes, and support intelligent decision -making. The engineer will develop autonomous workflows and Retrieval -Augmented Generation (RAG) systems with a focus on governance, security, and cost efficiency. The position requires close collaboration with developers, UX designers, business analysts, and systems analysts. The AI Agent Engineer will ensure that all solutions align with data privacy standards and enterprise -grade deployment practices.

Requirements

4 years of experience in AI/ML engineering or advanced data science.
4 years of proven experience building and deploying production -grade autonomous agents.
4 years of strong experience in context engineering.
4 years of experience with LangChain, LangGraph, CrewAI, or AutoGPT.
4 years of experience implementing RAG architectures using vector databases.
4 years of proficiency in Python and AI/ML libraries, including OpenAI, Hugging Face, and Azure AI.
4 years of experience integrating LLMs via APIs, including knowledge of AI governance, model lifecycle management, and evaluation.
4 years of experience implementing and extending the Model Context Protocol (MCP), as well as implementing AI guardrails, content filtering, and safety controls.
4 years of demonstrated understanding of data privacy and the handling of sensitive data, including PII and PHI.

Nice To Haves

2 years of experience building multi -agent or autonomous agentic workflows.
2 years of experience optimizing LLM cost, token usage, and performance.
2 years of familiarity with enterprise AI deployment patterns and scalability considerations.

Responsibilities

Design and develop AI -driven agentic solutions, including autonomous workflows and RAG systems.
Research, implement, and manage production -grade AI/ML software programs.
Integrate large language models (LLMs) via APIs to support intelligent decision -making and process automation.
Implement and extend the Model Context Protocol (MCP) to provide LLMs with secure, standardized access to local and remote data sources.
Build and deploy RAG architectures utilizing vector databases.
Apply AI guardrails, content filtering, and safety controls to ensure responsible AI use.
Manage AI governance, model lifecycle management, and evaluation processes.
Ensure proper handling of sensitive data, including PII and PHI, in compliance with data privacy standards.
Test and evaluate new AI programs and autonomous agent workflows.
Collaborate closely with developers, UX designers, business analysts, and systems analysts throughout the software development lifecycle.